2 papers
cs.AR2025
An Analytical Cost Model for Fast Evaluation of Multiple Compute-Engine CNN Accelerators
Fareed Qararyah, Mohammad Ali Maleki, Pedro Trancoso
Convolutional Neural Networks (CNNs) serve various applications with diverse performance and resource requirements. Model-aware CNN accelerators best address these diverse requirem…
cs.PF2024
Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs
Fareed Qararyah, Muhammad Waqar Azhar, Mohammad Ali Maleki +1
Depthwise and pointwise convolutions have fewer parameters and perform fewer operations than standard convolutions. As a result, they have become increasingly used in various compa…